Qwen: Qwen3 Coder 480B A35B

Text input Text output
Author's Description

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Key Specifications
Cost
$$$
Context
1M
Parameters
480B
Released
Jul 22, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Structured Outputs Tool Choice Response Format Seed Top P Max Tokens Temperature Presence Penalty
Features

This model supports the following features:

Tools Response Format Structured Outputs
Performance Summary

Qwen3 Coder 480B A35B demonstrates moderate speed performance, ranking in the 36th percentile across benchmarks, and offers competitive pricing, placing in the 54th percentile. A significant strength is its exceptional reliability, achieving a 97% success rate, indicating minimal technical failures. The model exhibits strong performance in agentic coding tasks, as evidenced by its 88.0% accuracy in the Coding (Baseline) benchmark, placing it in the 67th percentile. It also shows robust capabilities in Instruction Following (65.4% accuracy, 72nd percentile) and Reasoning (83.3% accuracy, 74th percentile), suggesting proficiency in complex problem-solving and adherence to directives. While its Email Classification accuracy is high at 98.0% (59th percentile), its Keyword Topic Relevance Classification is average at 90.0% (48th percentile). A notable weakness appears in Mathematics, where it scores 77.8% accuracy, ranking in the 40th percentile, and exhibits a particularly long duration for this task. Overall, the model is well-suited for its intended purpose of agentic coding, balancing competitive pricing with high reliability and strong performance in key coding and reasoning domains.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.22
Completion $0.95

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen3-coder-480b-a35b-07-25 1M $0.22 / 1M tokens $0.95 / 1M tokens
Hyperbolic
Hyperbolic | qwen/qwen3-coder-480b-a35b-07-25 262K $2 / 1M tokens $2 / 1M tokens
Parasail
Parasail | qwen/qwen3-coder-480b-a35b-07-25 262K $1 / 1M tokens $3 / 1M tokens
Targon
Targon | qwen/qwen3-coder-480b-a35b-07-25 262K $1 / 1M tokens $2 / 1M tokens
Alibaba
Alibaba | qwen/qwen3-coder-480b-a35b-07-25 1M $0.22 / 1M tokens $0.95 / 1M tokens
Alibaba
Alibaba | qwen/qwen3-coder-480b-a35b-07-25 262K $1.5 / 1M tokens $7.5 / 1M tokens
DeepInfra
DeepInfra | qwen/qwen3-coder-480b-a35b-07-25 262K $0.22 / 1M tokens $0.95 / 1M tokens
Chutes
Chutes | qwen/qwen3-coder-480b-a35b-07-25 262K $0.22 / 1M tokens $0.95 / 1M tokens
Novita
Novita | qwen/qwen3-coder-480b-a35b-07-25 262K $0.22 / 1M tokens $0.95 / 1M tokens
Novita
Novita | qwen/qwen3-coder-480b-a35b-07-25 262K $0.29 / 1M tokens $1.2 / 1M tokens
Together
Together | qwen/qwen3-coder-480b-a35b-07-25 262K $2 / 1M tokens $2 / 1M tokens
DeepInfra
DeepInfra | qwen/qwen3-coder-480b-a35b-07-25 262K $0.29 / 1M tokens $1.2 / 1M tokens
Chutes
Chutes | qwen/qwen3-coder-480b-a35b-07-25 262K $0.22 / 1M tokens $0.95 / 1M tokens
GMICloud
GMICloud | qwen/qwen3-coder-480b-a35b-07-25 262K $0.29 / 1M tokens $1.2 / 1M tokens
BaseTen
BaseTen | qwen/qwen3-coder-480b-a35b-07-25 262K $0.38 / 1M tokens $1.53 / 1M tokens
Phala
Phala | qwen/qwen3-coder-480b-a35b-07-25 262K $0.22 / 1M tokens $0.95 / 1M tokens
Cerebras
Cerebras | qwen/qwen3-coder-480b-a35b-07-25 131K $0.22 / 1M tokens $0.95 / 1M tokens
Cerebras
Cerebras | qwen/qwen3-coder-480b-a35b-07-25 131K $2 / 1M tokens $2 / 1M tokens
AtlasCloud
AtlasCloud | qwen/qwen3-coder-480b-a35b-07-25 262K $0.4 / 1M tokens $1.6 / 1M tokens
Fireworks
Fireworks | qwen/qwen3-coder-480b-a35b-07-25 262K $0.45 / 1M tokens $1.8 / 1M tokens
Nebius
Nebius | qwen/qwen3-coder-480b-a35b-07-25 262K $0.4 / 1M tokens $1.8 / 1M tokens
Google
Google | qwen/qwen3-coder-480b-a35b-07-25 262K $1 / 1M tokens $4 / 1M tokens
WandB
WandB | qwen/qwen3-coder-480b-a35b-07-25 262K $1 / 1M tokens $1.5 / 1M tokens
SiliconFlow
SiliconFlow | qwen/qwen3-coder-480b-a35b-07-25 262K $0.25 / 1M tokens $1 / 1M tokens
Chutes
Chutes | qwen/qwen3-coder-480b-a35b-07-25 262K $0.22 / 1M tokens $0.95 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen